Frizzled-related proteins 4 (SFRP4) rs1802073G allele predicts the elevated serum lipid levels during acitretin treatment in psoriatic patients from Hunan, China

Federated Machine Learning for Skin Lesion Diagnosis: An Asynchronous and Weighted Approach

The accurate and timely diagnosis of skin cancer is crucial as it can be a life-threatening disease. However, the implementation of traditional machine learning algorithms in healthcare settings is faced with significant challenges due to data privacy concerns. To tackle this issue, we propose a privacy-aware machine learning approach for skin cancer detection that utilizes asynchronous federated learning and convolutional neural networks (CNNs). Our method optimizes communication rounds by dividing the CNN layers into shallow and deep layers, with the shallow layers being updated more frequently. In order to enhance the accuracy and convergence of the central model, we introduce a temporally weighted aggregation approach that takes advantage of previously trained local models. Our approach is evaluated on a skin cancer dataset, and the results show that it outperforms existing methods in terms of accuracy and communication cost. Specifically, our approach achieves a higher accuracy rate while requiring fewer communication rounds. The results suggest that our proposed method can be a promising solution for improving skin cancer diagnosis while also addressing data privacy concerns in healthcare settings.

Pharmaco-Omics in Psoriasis: Paving the Way towards Personalized Medicine

The emergence of high-throughput approaches has had a profound impact on personalized medicine, evolving the identification of inheritable variation to trajectory analyses of transient states and paving the way for the unveiling of response biomarkers. The utilization of the multi-layered pharmaco-omics data, including genomics, transcriptomics, proteomics, and relevant biological information, has facilitated the identification of key molecular biomarkers that can predict the response to therapy, thereby optimizing treatment regiments and providing the framework for a tailored treatment plan. Despite the availability of multiple therapeutic options for chronic diseases, the highly heterogeneous clinical response hinders the alleviation of disease signals and exacerbates the annual burden and cost of hospitalization and drug regimens. This review aimed to examine the current state of the pharmaco-omic approaches performed in psoriasis, a common inflammatory disease of the skin. We sought to identify central studies that investigate the inter-individual variability and explore the underlying molecular mechanisms of drug response progression via biological profiling in psoriatic patients administered with the extended therapeutic armamentarium of psoriasis, incorporating conventional therapies, small molecules, as well as biological drugs that inhibit central pathogenic cytokines involved in the disease pathogenesis.

Towards Personalized Medicine in Psoriasis: Current Progress

Although innovative targeted therapies have positively revolutionized psoriasis treatment shifting treatment goals to complete or almost complete skin clearance, primary or secondary lack of efficacy is still possible. Hence, identifying robust biomarkers that reflect the various clinical psoriasis phenotypes would allow stratify patients in subgroups or endotypes, and tailor treatments according to the characteristics of each individual (precision medicine). To sum up the current progress in personalized medicine for psoriasis, we performed a review on the available evidence on biomarkers predictive of response to psoriasis treatments, with focus on phototherapy and systemic agents. Relevant literature published in English was searched for using the following databases from the last five years up to March 20, 2022: PubMed, Embase, Google Scholar, EBSCO, MEDLINE, and the Cochrane library. Currently, more evidence exists towards biologicals, as justified by the huge health care costs as compared to phototherapy or conventional systemic drugs. Among them, most of the studies focused on anti-TNF and IL12/23, with still few on IL17 (mainly secukinumab). The most discussed biomarker gene is the HLA-C*02:06 status that has been shown to be associated with psoriasis, and also differential response to biologicals. Although its positivity is associated with great response to MTX, debatable results were retrieved concerning both anti-TNF and IL12/23 while it seems not to affect secukinumab response. Personalized treatment in psoriasis would provide excellent outcome minimizing the risk of side effects. To date, although several candidates were proposed and assessed, the scarcity and heterogeneity of the results do not allow the identification of the gold-standard biomarker per each treatment. Anyway, the creation of a more comprehensive panel would be more reliable for the treatment decision process.

Polymorphisms of SLCO1B1 rs4149056 and SLC22A1 rs2282143 are associated with responsiveness to acitretin in psoriasis patients

Acitretin is widely used to treat psoriasis, but the efficacy varies significantly among individuals. To explore the association between polymorphisms and acitretin efficacy, we enrolled 46 and 105 Chinese Han psoriasis vulgaris patients for discovery and validation phases, respectively. The patients were treated with acitretin (30 mg/day) and calcipotriol ointment for at least 8 weeks, and their genotypes were detected. The wild-type genes and variants were transfected into HEK293 cells, which were then incubated with acitretin. The cellular acitretin concentration was measured by liquid chromatography-mass spectrometry. We found that the polymorphisms rs4149056 in the SLCO1B1 gene and rs2282143 in the SLC22A1 gene were associated with efficacy, both in the discovery (P = 0.013 and P = 0.002) and validation phases (P = 0.028 and P = 0.014), based on a 50% reduction from before to after treatment of the psoriasis area severity index (PASI50). When the PASI75 was used as an efficacy cutoff, a similar conclusion was drawn. The uptake of acitretin was lower with the rs4149056C (P = 0.002) and rs2282143T alleles (P = 0.038) than the wild-type alleles. Our results imply that the rs4149056C and rs2282143T variants decrease the acitretin uptake, and significantly associated with clinical effective responsiveness.